AI Security Engineer — Autonomous Agent Systems

Parameter; Baxter (TN); On-site; USD 180,000 - 240,000; Full time

Job summary

Parameter builds AI agents that perform autonomous penetration testing against production applications and cloud environments, identifying IDORs, broken access control, XSS, and misconfigurations.

You will design agent systems, including reasoning loops, tool interfaces, and memory architecture for a capable offensive security researcher mindset. This role is onsite in San Francisco, with a strong focus on production-grade LLM workflows and cost-aware inference.

Qualifications

• 3+ years of software engineering experience, including production LLM systems
• Strong TypeScript skills; comfortable with async and distributed systems
• Experience designing context engineering and reliable agent tooling
• Experience building or maintaining an eval harness; understanding offline vs production metrics
• Bonus: security background, CTF, bug bounty, or breaking things intentionally

Responsibilities

• Design and ship agent workflows in LangGraph and Temporal
• Build the tool layer used by agents: HTTP clients, auth handling, browser control, cloud enumeration, payload generation
• Own the eval loop and define what constitutes a good agent run
• Reduce false positives and optimize inference cost and latency
• Collaborate across product and customers; work across multiple product areas

Skills

Software engineering

TypeScript

Distributed systems

Workflow orchestration

Eval harness

Offline metrics

Context engineering

Security awareness

Tools

LangGraph

Temporal

GCP

AWS Bedrock

Anthropic API

Langfuse

Braintrust

GitHub Actions

Linear

Graphite

Job description

Parameter builds AI agents that perform autonomous penetration testing against production applications and cloud environments, identifying IDORs, broken access control, XSS, and misconfigurations.

You will design agent systems, including reasoning loops, tool interfaces, and memory architecture for a capable offensive security researcher mindset. This role is onsite in San Francisco, with a strong focus on production-grade LLM workflows and cost-aware inference.